Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add digital-stoic-org/agent-skills --skill scratchgit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/digital-stoic-org/agent-skills/scratch)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/scratch"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/scratch.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.00729 |
| Opus 5 | $0.00039 | $0.00365 |
| Sonnet 5 | $0.00016 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
scratch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scratch — Session Scratch Pad
Capture side-thoughts during deep work without breaking flow. Backing store: in-memory Task system (session-scoped, no persistence).
The whole point of this skill is to be invisible — capture the thought and get out of the way so the user stays in flow. Every interaction should feel instant: one-line confirmation, then resume exactly where the conversation was.
Commands
| Command | Action |
|---|---|
/scratch <text> |
Capture. Respond ✅ Scratch #N added. then resume prior work. |
/scratch list |
Show all notes numbered. |
/scratch rm <n> |
Delete note #n. |
/scratch clear |
Delete all notes, reset counter. |
Capture (/scratch <text>)
If no text provided, respond: ⚠️ Usage: /scratch <your thought here> — nothing else.
TaskList→ find maxdisplay_numwheremetadata.type === "scratch"(0 if none)TaskCreate:subject= verbatim text,description="scratch",metadata={"type": "scratch", "display_num": max+1}- Respond:
✅ Scratch #N added. - Resume prior conversation immediately. No commentary, no analysis, no reformulation.
List (/scratch list)
TaskList→ filtermetadata.type === "scratch", status not"deleted"- Display numbered by
display_num:
📋 Scratch pad (3)
1. revisit the endpoint naming
3. expose the ADRs read-only
5. OpenSpec doc is missing the 422 flow
If empty: 📋 Scratch pad is empty.
Remove (/scratch rm <n>)
If no number provided: ⚠️ Usage: /scratch rm <number>
TaskList→ find task wheremetadata.display_num === nandmetadata.type === "scratch"- If not found:
⚠️ Scratch #N not found. TaskUpdatewithstatus: "deleted"- Respond:
🗑️ Scratch #N removed.
Clear (/scratch clear)
TaskList→ all tasks withmetadata.type === "scratch"TaskUpdatestatus: "deleted"for each- Respond:
🗑️ Scratch pad cleared.
Key behaviors
- One-line responses only. Never add commentary, analysis, or suggestions about the note content.
- Resume immediately. After any scratch command, pick up the prior conversation exactly where it left off — mid-sentence if needed.
- Store verbatim. No cleanup, no categorization, no reformulation.
- Stable numbering. Gaps stay after deletion (1, 3, 5 is fine). Reset only on clear.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 66 lines · 78 tokens per session scan A 3ef9d9ab84db
scratch is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 729 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.